Xen CPUID

Contents

CPUID Overridden for Xen Hypervisor
CPUID Overridden for Xen Guests
Reference

CPUID Overridden for Xen Hypervisor

cpuid boot options definition

Xen hypervisor command line parameters are defined in:

xen-unstable/xen/arch/x86/cpu/intel.c:integer_param("cpuid_mask_ecx", opt_cpuid_mask_ecx);
xen-unstable/xen/arch/x86/cpu/intel.c:integer_param("cpuid_mask_edx", opt_cpuid_mask_edx);
xen-unstable/xen/arch/x86/cpu/amd.c:string_param("cpuid_mask_cpu", opt_famrev);
xen-unstable/xen/arch/x86/cpu/amd.c:integer_param("cpuid_mask_ecx", opt_cpuid_mask_ecx);
xen-unstable/xen/arch/x86/cpu/amd.c:integer_param("cpuid_mask_edx", opt_cpuid_mask_edx);
xen-unstable/xen/arch/x86/cpu/amd.c:integer_param("cpuid_mask_ext_ecx", opt_cpuid_mask_ext_ecx);
xen-unstable/xen/arch/x86/cpu/amd.c:integer_param("cpuid_mask_ext_edx", opt_cpuid_mask_ext_edx);

Intel cpu

For example, E8400 (Intel Core 2 Duo Processor series):
```
ecx = 0x0008E3FD
edx = 0xBFEBFBFF
```
when executing CPUID.EAX = 1 normally. If you want to rev down to E8400, you can set these values in these Xen boot parameters:
```
cpuid_mask_ecx=0x0008E3FD cpuid_mask_edx=0xBFEBFBFF
```

AMD cpu

There are some pre-canned values for overriding the CPUID features and extended features masks:

fam_0f_rev_c
fam_0f_rev_d
fam_0f_rev_e
fam_0f_rev_f
fam_0f_rev_g
fam_10_rev_b
fam_10_rev_c
fam_11_rev_b

The details of each cpu family is defined by:

} else if (!strcmp(opt_famrev, "fam_0f_rev_c")) {
        feat_ecx = AMD_FEATURES_K8_REV_C_ECX;
        feat_edx = AMD_FEATURES_K8_REV_C_EDX;
        extfeat_ecx = AMD_EXTFEATURES_K8_REV_C_ECX;
        extfeat_edx = AMD_EXTFEATURES_K8_REV_C_EDX;
} else if (!strcmp(opt_famrev, "fam_0f_rev_d")) {
        feat_ecx = AMD_FEATURES_K8_REV_D_ECX;
        feat_edx = AMD_FEATURES_K8_REV_D_EDX;
        extfeat_ecx = AMD_EXTFEATURES_K8_REV_D_ECX;
        extfeat_edx = AMD_EXTFEATURES_K8_REV_D_EDX;
} else if (!strcmp(opt_famrev, "fam_0f_rev_e")) {
        feat_ecx = AMD_FEATURES_K8_REV_E_ECX;
        feat_edx = AMD_FEATURES_K8_REV_E_EDX;
        extfeat_ecx = AMD_EXTFEATURES_K8_REV_E_ECX;
        extfeat_edx = AMD_EXTFEATURES_K8_REV_E_EDX;
} else if (!strcmp(opt_famrev, "fam_0f_rev_f")) {
        feat_ecx = AMD_FEATURES_K8_REV_F_ECX;
        feat_edx = AMD_FEATURES_K8_REV_F_EDX;
        extfeat_ecx = AMD_EXTFEATURES_K8_REV_F_ECX;
        extfeat_edx = AMD_EXTFEATURES_K8_REV_F_EDX;
} else if (!strcmp(opt_famrev, "fam_0f_rev_g")) {
        feat_ecx = AMD_FEATURES_K8_REV_G_ECX;
        feat_edx = AMD_FEATURES_K8_REV_G_EDX;
        extfeat_ecx = AMD_EXTFEATURES_K8_REV_G_ECX;
        extfeat_edx = AMD_EXTFEATURES_K8_REV_G_EDX;
} else if (!strcmp(opt_famrev, "fam_10_rev_b")) {
        feat_ecx = AMD_FEATURES_FAM10h_REV_B_ECX;
        feat_edx = AMD_FEATURES_FAM10h_REV_B_EDX;
        extfeat_ecx = AMD_EXTFEATURES_FAM10h_REV_B_ECX;
        extfeat_edx = AMD_EXTFEATURES_FAM10h_REV_B_EDX;
} else if (!strcmp(opt_famrev, "fam_10_rev_c")) {
        feat_ecx = AMD_FEATURES_FAM10h_REV_C_ECX;
        feat_edx = AMD_FEATURES_FAM10h_REV_C_EDX;
        extfeat_ecx = AMD_EXTFEATURES_FAM10h_REV_C_ECX;
        extfeat_edx = AMD_EXTFEATURES_FAM10h_REV_C_EDX;
} else if (!strcmp(opt_famrev, "fam_11_rev_b")) {
        feat_ecx = AMD_FEATURES_FAM11h_REV_B_ECX;
        feat_edx = AMD_FEATURES_FAM11h_REV_B_EDX;
        extfeat_ecx = AMD_EXTFEATURES_FAM11h_REV_B_ECX;
        extfeat_edx = AMD_EXTFEATURES_FAM11h_REV_B_EDX;

The detail of each value is defined in xen-unstable/xen/arch/x86/cpu/amd.h.

You can pass these hypervisor boot parameters in grub.conf. Each pair is equal to each other:

cpuid_mask_cpu=fam_0f_rev_c
cpuid_mask_ecx=0x0 cpuid_mask_edx=0x78BFBFF cpuid_mask_ext_ecx=0x0 cpuid_mask_ext_edx=0x0

cpuid_mask_cpu=fam_0f_rev_d
cpuid_mask_ecx=0x0 cpuid_mask_edx=0x78BFBFF cpuid_mask_ext_ecx=0x1 cpuid_mask_ext_edx=0x1

cpuid_mask_cpu=fam_0f_rev_e
cpuid_mask_ecx=0x1 cpuid_mask_edx=0x178BFBFF cpuid_mask_ext_ecx=0x3 cpuid_mask_ext_edx=0x3

cpuid_mask_cpu=fam_0f_rev_f
cpuid_mask_ecx=0x2001 cpuid_mask_edx=0x178BFBFF cpuid_mask_ext_ecx=0x1F cpuid_mask_ext_edx=0x1F

cpuid_mask_cpu=fam_0f_rev_g
cpuid_mask_ecx=0x2001 cpuid_mask_edx=0x178BFBFF cpuid_mask_ext_ecx=0x11F cpuid_mask_ext_edx=0x11F

cpuid_mask_cpu=fam_10_rev_b
cpuid_mask_ecx=0x802009 cpuid_mask_edx=0x178BFBFF cpuid_mask_ext_ecx=0x6FF cpuid_mask_ext_edx=0x6FF

cpuid_mask_cpu=fam_10_rev_c
cpuid_mask_ecx=0x802009 cpuid_mask_edx=0x178BFBFF cpuid_mask_ext_ecx=0x36FF cpuid_mask_ext_edx=0x36FF

cpuid_mask_cpu=fam_11_rev_b
cpuid_mask_ecx=0x2001 cpuid_mask_edx=0x178BFBFF cpuid_mask_ext_ecx=0x111F cpuid_mask_ext_edx=0x111F

CPUID Overridden for Xen Guests

xen-unstable/tools/examples/xmexample.hvm:

#-----------------------------------------------------------------------------
#   Configure guest CPUID responses:
#
#cpuid=[ '1:ecx=xxxxxxxxxxx00xxxxxxxxxxxxxxxxxxx,
#           eax=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx' ]
# - Unset the SSE4 features (CPUID.1[ECX][20-19])
# - Default behaviour for all other bits in ECX And EAX registers.
#
# Each successive character represent a lesser-significant bit:
#  '1' -> force the corresponding bit to 1
#  '0' -> force to 0
#  'x' -> Get a safe value (pass through and mask with the default policy)
#  'k' -> pass through the host bit value
#  's' -> as 'k' but preserve across save/restore and migration
#
#   Expose to the guest multi-core cpu instead of multiple processors
# Example for intel, expose a 8-core processor :
#cpuid=['1:edx=xxx1xxxxxxxxxxxxxxxxxxxxxxxxxxxx,
#          ebx=xxxxxxxx00010000xxxxxxxxxxxxxxxx',
#     '4,0:eax=001111xxxxxxxxxxxxxxxxxxxxxxxxxx']
#  - CPUID.1[EDX][HT] : Enable HT
#  - CPUID.1[EBX] : Number of vcpus * 2
#  - CPUID.4,0[EAX] : Number of vcpus * 2 - 1
#vcpus=8
#
# Example for amd, expose a 5-core processor :
# cpuid = ['1:ebx=xxxxxxxx00001010xxxxxxxxxxxxxxxx,
#             edx=xxx1xxxxxxxxxxxxxxxxxxxxxxxxxxxx',
# '0x80000001:ecx=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx1x',
# '0x80000008:ecx=xxxxxxxxxxxxxxxxxxxxxxxxxx001001']
#   - CPUID.1[EBX] : Threads per Core * Cores per Socket (2 * #vcpus)
#   - CPUID.1[EDX][HT] : Enable HT
#   - CPUID.0x80000001[CmpLegacy] : Use legacy method
#   - CPUID.0x80000008[ECX] : #vcpus * 2 - 1
#vcpus=5
#
#  Downgrade the cpuid to make a better compatibility for migration :
# Look like a generic 686 :
# cpuid = [ '0:eax=0x3,ebx=0x0,ecx=0x0,edx=0x0',
#           '1:eax=0x06b1,
#              ecx=xxxxxxxxxx0000xx00xxx0000000xx0,
#              edx=xx00000xxxxxxx0xxxxxxxxx0xxxxxx',
#           '4:eax=0x3,ebx=0x0,ecx=0x0,edx=0x0',
#  '0x80000000:eax=0x3,ebx=0x0,ecx=0x0,edx=0x0']
#  with the highest leaf
#  - CPUID.0[EAX] : Set the highest leaf
#  - CPUID.1[EAX] : 686
#  - CPUID.1[ECX] : Mask some features
#  - CPUID.1[EDX] : Mask some features
#  - CPUID.4 : Reply like the highest leaf, in our case CPUID.3
#  - CPUID.0x80000000 : No extension we are on a Pentium III, reply like the
#  highest leaf (CPUID.3).
#
#   Configure host CPUID consistency checks, which must be satisfied for this
#   VM to be allowed to run on this host's processor type:
#cpuid_check=[ '1:ecx=xxxxxxxxxxxxxxxxxxxxxxxxxx1xxxxx' ]
# - Host must have VMX feature flag set
#
# The format is similar to the above for 'cpuid':
#  '1' -> the bit must be '1'
#  '0' -> the bit must be '0'
#  'x' -> we don't care (do not check)
#  's' -> the bit must be the same as on the host that started this VM

Reference

AMD CPUID Specification: http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/25481.pdf
Intel(R) Processor Idientification and the CPUID Instruction: http://www.intel.com/Assets/PDF/appnote/241618.pdf
http://en.wikipedia.org/wiki/CPUID
CPUID dump tools for Linux: http://www.etallen.com/cpuid.html
Intel Processor Identification Utility: http://support.intel.com/support/processors/tools/piu